Subject: General Tech | March 26, 2015 - 12:32 PM | Jeremy Hellstrom
Tagged: hgst, western digital, helium, hdd
The new generation of helium filled HDD from HGST take their longevity seriously, rating them at 2.5 million hours MTBF. This generation also has 7 disks squeezed into the shell, with current capacities reaching 8TB and a shingled 10TB model currently being tested for release later this year. The increased life and storage density are only part of the benefits that helium brings, 23% lower operating power and temperatures 4-5°C lower than traditional drives will also have an impact on data centre operating costs. In their article The Register did ask how long the HelioSeal will keep the helium contained and while they did not get an exact figure, the 5 year warranty gives you a good idea of a lower limit.
"HGST has announced second-generation helium drive tech after shipping a million gen-1 Helium drives and upping field reliability by 15 per cent."
Here is some more Tech News from around the web:
- LibreOffice heads to the cloud in bid to take on Microsoft and Google @ The Inquirer
- Intel industrial solutions tool aims at faster IoT deployment @ The Inqurier
- TSMC to supply chips for rumored iPhone 6S and 6C @ DigiTimes
- And the prize for LEAST SECURE BROWSER goes to ... Chrome! @ The Register
- Google-gate: 'Toothless' watchdog FTC nibbles furiously on journalists @ The Register
- GTC 2015 In-depth Recap: Deep-learning, Quadro M6000, Autonomous Driving & More @ Techgage
Subject: Storage | March 10, 2015 - 03:44 PM | Allyn Malventano
Tagged: western digital, wdc, WD, Re+, hdd, 6tb, 5TB
Western Digital has just launched a new entry in their Datacenter Capacity HDD lineup:
The Re+ is based on the Re series of enterprise 3.5" HDDs (first revision reviewed here), but this one reduces the spin speed down from 7200 RPM to 5760 RPM. The HGST Ultrastar He6 is a great power efficient and Helium filled drive, but while that unit spins at 7200 RPM, it's max data rate is only 177 MB/sec. The 6TB WD RE spins at the same speed with a much higher rate of 225 MB/sec, but also draws more power than an He6. By reducing the platter speed, WD was able to bring power consumption into the 4.6-6.2W range with peak transfer rates of 175 MB/sec. The competing He6 draws 5.0-7.0W.
While dialing back the RPM was a simple way to achieve this very low power consumption, the He6 would still have the advantage in seek times (a faster spinning disk means less time waiting for the data to come around to the read head). The seek time argument may be moot given the purpose of these HDDs leans towards cold/warm/archival data storage that is very infrequently and sporadically accessed. Still, it is an interesting point that WD's platter density was so much higher that they could simply slow the RPM and yet maintain throughputs competitive with a faster spinning unit.
In combination with this announcement is the fact that the Re and Se lines (formerly limited to 4TB) are now available in 5TB and 6TB capacities. With the Se moving up to 6TB, we may see a Red Pro in the same capacity in the near future (depending on demand).
More to follow on these at a future date. Full press blast after the break.
Subject: General Tech | January 26, 2015 - 01:15 PM | Jeremy Hellstrom
Tagged: statistics, mtbf, hdd, backblaze
Backblaze is a moderately sized hosting company with about 40,000 disks set up in their own style of arrays called Storage Pods, which are open sourced so that you can build one yourself if you so desire. Every once and a while they put out reliability numbers for the HDDs that they use in their arrays; the newest report just arrived for your perusal. This is good as most reliability and market share studies are done by professional organizations which they tend to charge quite a bit for their findings as they do put a lot of effort into ensuring that their data is correct. Unfortunately that also means that most people do not have access to the information and make judgments based on incomplete or incorrect data. As The Register points out, 40,000 HDDs is a very small sample size compared to the market as a whole or even large hosting companies and so the data set you can see here may not be the best representation of the actual market failure rates projected from it may not be overly accurate. On the other hand it is nice to have any data, especially when you are provided with the actual sample size and a definition of failure. If you are really into the numbers game, spend some time researching the Mean Time Between Failure and Average Failure Rate and the ongoing debate on how to properly measure expected mortality rates among large drives.
"We're not entirely comfortable with cloud backup outfit Backblaze's data on disk drive reliability, but the company has just popped out another year's worth of analysis on which drives hang around longest. With due scepticism, let's have a look."
Here is some more Tech News from around the web:
- Hands-on With Windows 10’s Preview Build 9926 @ Techgage
- SURPRISE! Microsoft pops open Windows 10 Preview build early @ The Register
- We Can’t Wait to Try Leatherman’s New Wearable @ MAKE:Blog
- Apple's iPhone 7 chip will reportedly be supplied by Samsung Electronics @ The Inquirer
- Tenda AV1000 Gigabit Powerline Adapter @ eTeknix
Subject: Storage, Shows and Expos | January 4, 2015 - 05:15 PM | Allyn Malventano
Tagged: CES, western digital, storage visions, ssd, SATA Express, hybrid, hdd, ces 2015
At the SATA-IO booth at Storage Visions, they have a functional demo of Western Digital prototype hybrid HDD/SSD's.
These are not hybrid in the traditional sense, as the SSD portion (128GB JMicron based controller driving Toshiba flash in the case of these prototypes) is logically separated from the HDD portion (a standard 4TB Black in this case).
Given that a SATA Express link can simultaneously pass a PCIe 2.0 x2 link in addition to a SATA 6Gbit/sec link, this one unit can link an SSD and an HDD simultaneously and independently. Above you see the standard SATA Express connector, and below is how those pins are connected at the drive itself:
Note the additional pins at what is usually the black side of the connector.
The rest of the connector is mostly a standard SATA connector that you are used to seeing.
At the demo, we saw a single 3.5" hybrid unit booting from the SSD portion and using the 4TB HDD for mass storage, all from the same device. The second demo had a separate boot drive and linked a pair of these prototype units in a dual RAID. Configured through Windows dynamic volumes, a RAID of the HDD's offered the increased performance you might expect from a pair of 4TB WD Blacks. The SSD portion of each unit was also RAIDed, and we saw their combined throughput as just over 1GB/sec. That was not much more than what a pair of RAIDed SATA 6Gb/sec SSDs would do, but realize this was being accomplished in addition to (and independently of) the HDD portions.
We were not allowed to start removing screws, but here's a look at the accessible portion of the logic board for this drive:
There is a JMicron controller paired with a single package of Toshiba flash. Toshiba has shown they can contain 128GB in a single package, so no problems there.
We're not sure where this technology is headed as the recent trend has been towards sticking with the standard SATA link for mass storage and M.2 SSDs plugged directly into the added port we've been seeing in many recent motherboards. We'll keep an eye on this technology moving forward, but for now at least we have seen it in the flesh and fully functional.
Follow all of our coverage of the show at http://pcper.com/ces!
Subject: Storage | December 15, 2014 - 01:35 PM | Jeremy Hellstrom
Tagged: SAS, hdd, DIY, LSI, Seagate, icy dock
You may want to build a server consisting of enterprise level SSDs to make sure it provides the best possible speeds to anyone accessing data stored there but the chances of you getting the budget for it are slim going on none. That is why reading the guide on building servers from Modders Inc is worth your time if you find yourself pondering the best way to build a storage server on a budget without making it abysmally slow. You have many choices when you are designing a storage server but if you are not quite sure where to start the list of components and the arguments for their usefulness will get you headed in the right direction. For example the LSI MegaRAID SAS 9271-8i is an impressive RAID controller and with good SAS HDDs you can expect to see very good data throughput and will be more important than the CPU you select. Check out the article right here.
"IT infrastructure and storage has always been part of serious conversation between IT engineers and their bosses. As always IT Engineers want to use the best of the newest technologies while their bosses want to keep every project under a tight budget. It's always an ongoing battle, however both sides always come to some mutual agreement that benefits both sides."
Here are some more Storage reviews from around the web:
- Western Digital Red (WD60EFRX) 6 TB Hard Disk @ TechARP
- QNAP TS-451 Network Attached Storage @ Modders-Inc
- LaCie d2 Thunderbolt Review @ TechwareLabs
- Inateck FE2005 USB 3.0 Tool-Less 2.5″ HDD Enclosure @ eTeknix
- Transcend SSD370 256GB SSD Review @HiTech Legion
- Samsung 850 EVO 500GB SSD Review @ NikKTech
- Samsung 850 EVO 120GB review @ Bjorn3d
- Kingston SSDnow M2 SATA 120GB Solid State Drive @ eTeknix
Subject: General Tech | December 9, 2014 - 01:26 PM | Jeremy Hellstrom
Tagged: HAMR, Seagate, hdd, TDMR
Seagate has been talking about HAMR for many years now but is finally getting close to being able to provide a working product. Currently they use perpendicular magnetic recording which should reach an areal density of 850/900Gbit/in2 in the coming year with a shingled version hitting 1Tbit/in2. Shingled platters store data in slightly smaller and overlapping tracks reminiscent of a shingled roof. In 2016 Seagate predicts the arrival of TDMR which will start at the same density as shingled PMR with an increase to 1.3Tbit/in2 when set up in a shingled format. 2017 is the tentative date for the arrival of the brand new technology and as of now Seagate is predicting an aureal density somewhere in the neighbourhood of 2Tbit/in2. The performance will never match that of flash based drives but the cost per gigabyte will be far more attractive for those who have more of a need to store large amounts of data than to have high speed access. Check out more at The Register.
"We have better visibility into Seagate’s view of the ending of the current perpendicular magnetic recording (PMR) era. The ending is delayed by narrowing the tracks so as to cram more of them on a platter. This is called two-dimensional magnetic recording (TDMR) and should arrive in 2016."
Here is some more Tech News from around the web:
- Canonical makes Ubuntu more snappy with Docker @ The Inquirer
- Blackphone launches privacy-aware app store in bid to reward security-conscious devs @ The Inquirer
- Zombie POODLE wanders in, cocks leg on TLS @ The Register
- Interview with UK gaming system builder CHILLBLAST @ K
- The Samsung Holiday Gift Guide @ TechARP
- The Dell Holiday Gift Guide @ TechARP
Subject: General Tech | November 4, 2014 - 12:44 PM | Jeremy Hellstrom
Tagged: Seagate, Kinetic, hdd, openstack
Bringing down the cost of storage is a big focus now as files continue to grow in size and retention becomes more popular with even casual users. Services like Amazon and Netflix require huge amounts of storage to keep their products on and every penny they can squeeze results in better profits for themselves and shareholders. Seagate is addressing this with their new Kinect, a type of HDD which connects directly over Ethernet without needing server infrastructure to work. There is a working demonstration of this technology using Bigfoot JBOD at OpenStack and AOL is at least somewhat interested in testing arrays of these drives. The Register offers a bit more information here, hopefully more will be forthcoming after the OpenStack conference wraps up.
"Kinetic is a disk drive directly addressed over Ethernet using Get and Put-style object storage commands using an open source API. The idea is that applications can directly use banks of these drives without having to go through complex filesystem software stacks or block access protocols and storage array controllers."
Here is some more Tech News from around the web:
- Microsoft reportedly plans to develop larger Surface Pro tablet @ DigiTimes
- Intel: A tiny video drone? Disguised as a BRACELET? Great! Take half a million dollars! @ The Register
- Mac OS X Yosemite has a root access vulnerability @ The Inquirer
- Samsung, TSMC still competing for Apple A9 chip orders @ DigiTimes
- Super-villains of C sought for WORLD CONQUEST plan @ The Register
- Flaw in New Visa Cards Would Let Hackers Steal $1M Per Card @ Slashdot
- Microsoft offers preview of real-time translation service for Skype @ The Inquirer
- How to Find the Best Linux Distribution for a Specific Task @ Linux.com
Subject: Storage | November 1, 2014 - 08:10 PM | Tim Verry
Tagged: toshiba, sata 3, hdd, Hard Drive, 7200 rpm, 5TB, 4TB
This week, Toshiba introduced 4TB and 5TB hard drives to the consumer space. Coming from Toshiba's Digital Products Division, the new drives are part of the company's PH3*00U-1I72 series and are the first four and five Terabyte 3.5" consumer hard drives sporting 7200 RPM spindle speeds (though enterprise and NAS focused drives have been available prior to these new drives).
The new 4TB and 5TB HDDs are 3.5-inch desktop drives with four and five platters respectively. Toshiba is using Perpendicular Magnetic Recording (PMR) and Tunnel Magneto-Resistive (TMR) technologies to hit 1TB per platter. The 7,200 RPM spindle speed allows Toshiba to hit an average seek time of 10.5ms, and the 128MB of cache stores frequently accessed data. The new drives are paired with a SATA 3 6Gbps interface. Toshiba has included NCQ (Native Command Queuing) support along with shock sensors and ramp on/off loading safety features.
The 4TB drive has an MSRP of $299 while the 5TB model has an MSRP of $399. Fortunately for digital hoarders, the drives are currently selling at prices below the MSRP. The 5TB model is being priced around $320 while the 4TB model is priced between $220 and $240 at the time of writing depending on your retailer of choice.
Subject: Storage, Shows and Expos | September 9, 2014 - 04:51 PM | Allyn Malventano
Tagged: WDC< Western Digital, WD, idf 2014, idf, hdd, Cold, Archival, Ae
We talked about helium filled, shingled HDD's from HGST earlier today. Helium may give you reduced power demands, but at the added expensive of hermetically sealed enclosures over conventional HDD's. Shingling may give added capacity, but at the expense of being forced into specific writing methods. Now we know Western Digital's angle into archival / cold storage:
..so instead of going with higher cost newer technologies, WD is taking their consumer products and making them more robust. They are also getting rid of the conventional thinking of capacity increments and are moving to 100GB increments. The idea is that once a large company or distributor has qualified a specific HDD model on their hardware, that model will stick around for a while, but be continued at an increased capacity as platter density yields increase over time. WD has also told me that capacities may even be mixed an matched within a 20-box of drives, so long as the average capacity matches the box label. This works in the field of archival / cold storage for a few reasons:
- Archival storage systems generally do not use conventional RAID (where an entire array of matching capacity disks are spinning simultaneously). Drives are spun up and written to individually, or spun up individually to service the occasional read request. This saves power overall, and it also means the individual drives can vary in capacity with no ill effects.
- Allowing for variable capacity binning helps WD ship more usable platters/drives overall (i.e. not rejecting drives that can't meet 6TB). This should drive overall costs down.
- Increasing capacity by only a few hundred GB per drive turns into *huge* differences in cost when you scale that difference up to the number of drives you would need to handle a very large total capacity (i.e. Exabytes).
So the idea here is that WD is choosing to stick with what they do best, which they can potentially do for even cheaper than their consumer products. That said, this is really meant for enterprise use and not as a way for a home power user to save a few bucks on a half-dozen drives for their home NAS. You really need an infrastructure in place that can handle variable capacity drives seamlessly. While these drives do not employ SMR to get greater capacity, that may work out as a bonus, as writes can be performed in a way that all systems are currently compatible with (even though I suspect they will be tuned more for sequential write workloads).
Here's an illustration of this difference:
The 'old' method meant that drives on the left half of the above bell curve would have to be sold as 5TB units.
With the 'new' method, drives can be sold based on a spec closer to their actual capacity yield. For a given model, shipping capacities would increase as time goes on (top to bottom of the above graphic).
To further clarify what is meant by the term 'cold storage' - the data itself is cold, as in rarely if ever accessed:
Examples of this would be Facebook posts / images from months or years ago. That data may be rarely touched, but it needs to be accessible enough to be browsed to via the internet. The few second archival HDD spinup can handle this sort of thing, while a tape system would take far too long and would likely timeout that data request.
Subject: Storage, Shows and Expos | September 9, 2014 - 02:00 PM | Allyn Malventano
Tagged: ssd, SMR, pcie, NVMe, idf 2014, idf, hgst, hdd, 10TB
It's the first day of IDF, so it's only natural that we see a bunch of non-IDF news start pouring out :). I'll kick them off with a few announcements from HGST. First item up is their new SN100 line of PCIe SSDs:
These are NVMe capable PCIe SSDs, available from 800GB to 3.2TB capacities and in (PCI-based - not SATA) 2.5" as well as half-height PCIe cards.
Next up is an expansion of their HelioSeal (Helium filled) drive line:
Through the use of Shingled Magnetic Recording (SMR), HGST can make an even bigger improvement in storage densities. This does not come completely free, as due to the way SMR writes to the disk, it is primarily meant to be a sequential write / random access read storage device. Picture roofing shingles, but for hard drives. The tracks are slightly overlapped as they are written to disk. This increases density greatly, but writting to the middle of a shingled section is not possible without potentially overwriting two shingled tracks simultaneously. Think of it as CD-RW writing, but for hard disks. This tech is primarily geared towards 'cold storage', or data that is not actively being written. Think archival data. The ability to still read that data randomly and on demand makes these drives more appealing than retrieving that same data from tape-based archival methods.
Further details on the above releases is scarce at present, but we will keep you posted on further details as they develop.